AI Strategy - natural language to trades
56
39%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./src/skills/bundled/ai-strategy/SKILL.mdSecurity
2 findings — 2 medium severity. This skill can be installed but you should review these findings before use.
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Third-party content exposure detected (high risk: 1.00). The skill fetches live price data from the public API https://price.jup.ag/v4/price (see checkStrategy and getSolPrice) and directly uses those responses to decide and execute trades, so untrusted third‑party content can materially influence agent actions.
The skill is specifically designed for direct financial operations, giving the agent the ability to move money or execute financial transactions — such as payment processing, cryptocurrency operations, banking integrations, or market order execution.
Direct money access detected (high risk: 1.00). The skill is explicitly built to create and run trading strategies and to execute trades. It defines an /execute command with examples like "buy 0.5 SOL", "sell all BONK", "swap 1 SOL to USDC", and includes DCA, stop-loss, ladder orders, and immediate execution semantics. It also references on-chain trading infrastructure (Jupiter routes, Solana SPL tokens) and periodic monitoring that "executes trade when condition met." These are specific crypto/market-order capabilities to send transactions and move funds, not generic tooling — therefore it grants direct financial execution authority.
2a8c94e
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.